| name | graph-context |
| description | Dual-graph code context retrieval. Use automatically at the start of every task to get relevant files and symbols before exploring the codebase. |
Dual-Graph Context Policy
You have a dual-graph MCP server that provides efficient, structural code context retrieval.
MANDATORY: Always follow this order
-
Call graph_continue first — before any file exploration, grep, or code reading.
-
If graph_continue returns needs_project=true: call graph_scan with the
current project directory. Do NOT ask the user.
-
If graph_continue returns skip=true: project has fewer than 5 files.
Do NOT do broad or recursive exploration. Read only specific files if their names
are mentioned, or ask the user what to work on.
-
Read recommended_files using graph_read — one call per file.
graph_read accepts a single file parameter (string). Call it separately for each
recommended file. Do NOT pass an array or batch multiple files into one call.
recommended_files may contain file::symbol entries (e.g. src/auth.ts::handleLogin).
Pass them verbatim to graph_read(file: "src/auth.ts::handleLogin") — it reads only
that symbol's lines, not the full file.
-
Check confidence and obey the caps strictly:
confidence=high -> Stop. Do NOT grep or explore further.
confidence=medium -> If recommended files are insufficient, call fallback_rg
at most max_supplementary_greps time(s), then graph_read
at most max_supplementary_files additional file(s). Then stop.
confidence=low -> Call fallback_rg at most max_supplementary_greps time(s),
then graph_read at most max_supplementary_files file(s). Then stop.
Rules
- Do NOT use
rg, grep, or bash file exploration before calling graph_continue.
- Do NOT do broad/recursive exploration at any confidence level.
max_supplementary_greps and max_supplementary_files are hard caps — never exceed them.
- After edits, call
graph_register_edit with the changed files. Use file::symbol notation
when the edit targets a specific function, class, or hook.